서브메뉴
검색
Structured Information Extraction and Applications in Complex Reasoning
Structured Information Extraction and Applications in Complex Reasoning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153043
- ISBN
- 9798346764472
- DDC
- 020
- 저자명
- Su, Xin.
- 서명/저자
- Structured Information Extraction and Applications in Complex Reasoning
- 발행사항
- [Sl] : The University of Arizona, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 117 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Bethard, Steven.
- 학위논문주기
- Thesis (Ph.D.)--The University of Arizona, 2024.
- 초록/해제
- 요약Structured information is generally easier to store, understand, and utilize compared to unstructured text. Extracting structured information from unstructured text and applying this extracted information to various tasks and use cases has been a longstanding research area. In this dissertation, we address both the extraction of structured information and its application to complex reasoning tasks.For structured information extraction, we focus on temporal information extraction, particularly on temporal normalization. Through systematic comparative experiments, we propose a strategy that enhances the generalization capability of time expression recognition systems-the crucial first step in the temporal normalization task-in new domains. Additionally, we introduce a semantic parsing framework based on large language models for end-to-end temporal expression recognition.Regarding the application of structured information, we focus on two tasks: temporal reasoning and open-domain multi-hop reasoning. In temporal reasoning, we combine extracted temporal graphs with Transformer-based question-answering systems, significantly improving their temporal reasoning capabilities. For the open-domain multi-hop reasoning task, we propose a semi-structured chain-of-thought approach that effectively integrates structured knowledge graphs, unstructured text, and parametric knowledge within large language models to answer knowledge-intensive questions.
- 일반주제명
- Information science
- 일반주제명
- Computer science
- 기타저자
- The University of Arizona Information
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164765
■00520250211153043
■006m o d
■007cr#unu||||||||
■020 ▼a9798346764472
■035 ▼a(MiAaPQ)AAI31639477
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a020
■1001 ▼aSu, Xin.▼0(orcid)0000-0002-2712-2804
■24510▼aStructured Information Extraction and Applications in Complex Reasoning
■260 ▼a[Sl]▼bThe University of Arizona▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a117 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Bethard, Steven.
■5021 ▼aThesis (Ph.D.)--The University of Arizona, 2024.
■520 ▼aStructured information is generally easier to store, understand, and utilize compared to unstructured text. Extracting structured information from unstructured text and applying this extracted information to various tasks and use cases has been a longstanding research area. In this dissertation, we address both the extraction of structured information and its application to complex reasoning tasks.For structured information extraction, we focus on temporal information extraction, particularly on temporal normalization. Through systematic comparative experiments, we propose a strategy that enhances the generalization capability of time expression recognition systems-the crucial first step in the temporal normalization task-in new domains. Additionally, we introduce a semantic parsing framework based on large language models for end-to-end temporal expression recognition.Regarding the application of structured information, we focus on two tasks: temporal reasoning and open-domain multi-hop reasoning. In temporal reasoning, we combine extracted temporal graphs with Transformer-based question-answering systems, significantly improving their temporal reasoning capabilities. For the open-domain multi-hop reasoning task, we propose a semi-structured chain-of-thought approach that effectively integrates structured knowledge graphs, unstructured text, and parametric knowledge within large language models to answer knowledge-intensive questions.
■590 ▼aSchool code: 0009.
■650 4▼aInformation science
■650 4▼aComputer science
■653 ▼aComplex reasoning
■653 ▼aNatural language processing
■653 ▼aQuestion answering
■653 ▼aTime normalization
■690 ▼a0723
■690 ▼a0984
■690 ▼a0800
■71020▼aThe University of Arizona▼bInformation.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0009
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164765▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
